© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57520
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omik
    -0.09
    omat
    -0.08
    алÑĸз
    -0.07
    ÙĦÛĮسÛĮ
    -0.07
    uide
    -0.07
    reak
    -0.07
    eka
    -0.07
     плÑı
    -0.07
    usi
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
     barg
    0.07
    atsapp
    0.06
     Hogan
    0.06
     Theodore
    0.06
    ucker
    0.06
     biên
    0.06
    å¾ħ
    0.06
     zab
    0.06
     salv
    0.05
    agi
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.